Papers › SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

22 Aug 2023arXiv:2308.11596archive 2025-07-28

Seamless Communication, Loïc Barrault, Yu-An Chung, Mariano Cora Meglioli, David Dale, Ning Dong, Paul-Ambroise Duquenne, Hady Elsahar, Hongyu Gong, Kevin Heffernan, John Hoffman, Christopher Klaiber, Pengwei Li, Daniel Licht, Jean Maillard, Alice Rakotoarison, Kaushik Ram Sadagopan, Guillaume Wenzek, Ethan Ye, Bapi Akula, Peng-Jen Chen, Naji El Hachem, Brian Ellis, Gabriel Mejia Gonzalez, Justin Haaheim, Prangthip Hansanti, Russ Howes, Bernie Huang, Min-Jae Hwang, Hirofumi Inaguma, Somya Jain, Elahe Kalbassi, Amanda Kallet, Ilia Kulikov, Janice Lam, Daniel Li, Xutai Ma, Ruslan Mavlyutov, Benjamin Peloquin, Mohamed Ramadan, Abinesh Ramakrishnan, Anna Sun, Kevin Tran, Tuan Tran, Igor Tufanov, Vish Vogeti, Carleigh Wood, Yilin Yang, Bokai Yu, Pierre Andrews, Can Balioglu, Marta R. Costa-jussà, Onur Celebi, Maha Elbayad, Cynthia Gao, Francisco Guzmán, Justine Kao, Ann Lee, Alexandre Mourachko, Juan Pino, Sravya Popuri, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Paden Tomasello, Changhan Wang, Jeff Wang, Skyler Wang

What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed machine translation coverage beyond 200 languages, unified speech-to-speech translation models have yet to achieve similar strides. More specifically, conventional speech-to-speech translation systems rely on cascaded systems that perform translation progressively, putting high-performing unified systems out of reach. To address these gaps, we introduce SeamlessM4T, a single model that supports speech-to-speech translation, speech-to-text translation, text-to-speech translation, text-to-text translation, and automatic speech recognition for up to 100 languages. To build this, we used 1 million hours of open speech audio data to learn self-supervised speech representations with w2v-BERT 2.0. Subsequently, we created a multimodal corpus of automatically aligned speech translations. Filtered and combined with human-labeled and pseudo-labeled data, we developed the first multilingual system capable of translating from and into English for both speech and text. On FLEURS, SeamlessM4T sets a new standard for translations into multiple target languages, achieving an improvement of 20% BLEU over the previous SOTA in direct speech-to-text translation. Compared to strong cascaded models, SeamlessM4T improves the quality of into-English translation by 1.3 BLEU points in speech-to-text and by 2.6 ASR-BLEU points in speech-to-speech. Tested for robustness, our system performs better against background noises and speaker variations in speech-to-text tasks compared to the current SOTA model. Critically, we evaluated SeamlessM4T on gender bias and added toxicity to assess translation safety. Finally, all contributions in this work are open-sourced and accessible at https://github.com/facebookresearch/seamless_communication

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 2 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/seamless_communication officialmentioned in paperpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
facebookresearch/sonar mentioned in paperpytorchNOASSERTIONSyntology: not harvested report
pwc-1/Paper-10 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large... (arXiv:2403.07714; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 2 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/University mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (arXiv:2409.12191; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong

Licence: 2 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from facebookresearch/seamless_communication. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

facebookresearch/seamless_communication official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
add_inference_arguments src/seamless_communication/cli/m4t/predict/predict.py ran · our draft was wrong licence not identified · pointer only · 9f6a6a6199e1dc32 · report fixture: signature parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-22
remove_prosody_tokens_from_text src/seamless_communication/cli/expressivity/predict/predict.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 6a4229d04ccaa9d4 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22

Tasks

Automatic Speech RecognitionMachine TranslationSpeech-to-Speech TranslationSpeech-to-TextSpeech-to-Text TranslationText to SpeechTranslationtext-to-speechtext-to-speech translation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Machine Translation FLoRes-200 SeamlessM4T-Large-V1 BLEU 37.5 #3 of 5 Archive leaderboard report
Machine Translation flores95-devtest X-eng SeamlessM4T Large ChrF++ 60.8 #1 of 3 Archive leaderboard report
Machine Translation flores95-devtest X-eng SeamlessM4T-NLLB-1.3B ChrF++ 60.7 #2 of 3 Archive leaderboard report
Machine Translation flores95-devtest X-eng SeamlessM4T Medium ChrF++ 55.4 #3 of 3 Archive leaderboard report
Machine Translation flores95-devtest eng-X SeamlessM4T Large ChrF++ 50.9 #1 of 3 Archive leaderboard report
Machine Translation flores95-devtest eng-X SeamlessM4T-NLLB-1.3B ChrF++ 49.6 #2 of 3 Archive leaderboard report
Machine Translation flores95-devtest eng-X SeamlessM4T Medium ChrF++ 48.4 #3 of 3 Archive leaderboard report
Speech-to-Speech Translation CVSS SeamlessM4T Large ASR-BLEU 36.5 #1 of 2 Archive leaderboard report
Speech-to-Speech Translation CVSS SeamlessM4T Large Parameters 2.3B #1 of 2 Archive leaderboard report
Speech-to-Speech Translation CVSS SeamlessM4T Medium ASR-BLEU 28.1 #2 of 2 Archive leaderboard report
Speech-to-Speech Translation CVSS SeamlessM4T Medium Parameters 1.2B #2 of 2 Archive leaderboard report
Speech-to-Speech Translation FLEURS X-eng SeamlessM4T LargeV2 ASR-BLEU 29.4 #3 of 7 Archive leaderboard report
Speech-to-Speech Translation FLEURS X-eng SeamlessM4T Large ASR-BLEU 25.8 #4 of 7 Archive leaderboard report
Speech-to-Speech Translation FLEURS X-eng SeamlessM4T Medium ASR-BLEU 20.4 #7 of 7 Archive leaderboard report
Speech-to-Text Translation CoVoST 2 X-eng SeamlessM4T Large BLEU 34.1 #1 of 2 Archive leaderboard report
Speech-to-Text Translation CoVoST 2 X-eng SeamlessM4T Medium BLEU 29.8 #2 of 2 Archive leaderboard report
Speech-to-Text Translation CoVoST 2 eng-X SeamlessM4T Large BLEU 30.6 #1 of 2 Archive leaderboard report
Speech-to-Text Translation CoVoST 2 eng-X SeamlessM4T Medium BLEU 26.6 #2 of 2 Archive leaderboard report
Speech-to-Text Translation FLEURS X-eng SeamlessM4T Large BLEU 24.0 #1 of 2 Archive leaderboard report
Speech-to-Text Translation FLEURS X-eng SeamlessM4T Medium BLEU 20.9 #2 of 2 Archive leaderboard report
Speech-to-Text Translation FLEURS eng-X SeamlessM4T Large BLEU 21.5 #1 of 2 Archive leaderboard report
Speech-to-Text Translation FLEURS eng-X SeamlessM4T Medium BLEU 19.2 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections